基于磁共振成像延迟钆增强区分心肌梗死与心肌炎的影像组学研究：与主观视觉分析的比较
Radiomics for Distinguishing Myocardial Infarction from Myocarditis at Late Gadolinium Enhancement at MRI: Comparison with Subjective Visual Analysis.
作者信息
Di Noto Tommaso, von Spiczak Jochen, Mannil Manoj, Gantert Elena, Soda Paolo, Manka Robert, Alkadhi Hatem
机构信息
Institute of Diagnostic and Interventional Radiology (T.D.N., J.v.S., M.M., E.G., R.M., H.A.) and Department of Cardiology, University Heart Center (R.M.), University Hospital Zurich, University of Zurich, Raemistr 100, CH-8091, Zurich, Switzerland; Unit of Computer Systems and Bioinformatics, University Campus Bio-Medico of Rome, Rome, Italy (T.D.N., P.S.); and Institute for Biomedical Engineering, University and ETH Zurich (R.M.).
出版信息
Radiol Cardiothorac Imaging. 2019 Dec 19;1(5):e180026. doi: 10.1148/ryct.2019180026. eCollection 2019 Dec.
PURPOSE
To evaluate whether radiomics features of late gadolinium enhancement (LGE) regions at cardiac MRI enable distinction between myocardial infarction (MI) and myocarditis and to compare radiomics with subjective visual analyses by readers with different experience levels.
MATERIALS AND METHODS
In this retrospective, institutional review board-approved study, consecutive MRI examinations of 111 patients with MI and 62 patients with myocarditis showing LGE were included. By using open-source software, classification performances attained from two-dimensional (2D) and three-dimensional (3D) texture analysis, shape, and first-order descriptors were compared, applying five different machine learning algorithms. A nested, stratified 10-fold cross-validation was performed. Classification performances were compared through Wilcoxon signed-rank tests. Supervised and unsupervised feature selection techniques were tested; the effect of resampling MR images was analyzed. Subjective image analysis was performed on 2D and 3D image sets by two independent, blinded readers with different experience levels.
RESULTS
When trained with recursive feature elimination (RFE), a support vector machine achieved the best results (accuracy: 88%) for 2D features, whereas linear discriminant analysis (LDA) showed the highest accuracy (85%) for 3D features ( <.05). When trained with principal component analysis (PCA), LDA attained the highest accuracy with both 2D (86%) and 3D (89%; =.4) features. Results found for classifiers trained with spline resampling were less accurate than those achieved with one-dimensional (1D) nearest-neighbor interpolation ( <.05), whereas results for classifiers trained with 1D nearest-neighbor interpolation and without resampling were similar ( =.1). As compared with the radiomics approach, subjective visual analysis performance was lower for the less experienced and higher for the experienced reader for both 2D and 3D data.
CONCLUSION
Radiomics features of LGE permit the distinction between MI and myocarditis with high accuracy by using either 2D features and RFE or 3D features and PCA.© RSNA, 2019
目的
评估心脏磁共振成像（MRI）晚期钆增强（LGE）区域的影像组学特征能否区分心肌梗死（MI）和心肌炎，并将影像组学与不同经验水平的阅片者进行的主观视觉分析进行比较。
材料与方法
在这项经机构审查委员会批准的回顾性研究中，纳入了111例MI患者和62例显示LGE的心肌炎患者的连续MRI检查。使用开源软件，应用五种不同的机器学习算法，比较二维（2D）和三维（3D）纹理分析、形状和一阶描述符获得的分类性能。进行了嵌套分层的10倍交叉验证。通过Wilcoxon符号秩检验比较分类性能。测试了监督和非监督特征选择技术；分析了重采样MR图像的效果。由两名经验水平不同的独立、盲法阅片者对2D和3D图像集进行主观图像分析。
结果
当采用递归特征消除（RFE）进行训练时，支持向量机对2D特征取得了最佳结果（准确率：88%），而线性判别分析（LDA）对3D特征显示出最高准确率（85%）（P<.05）。当采用主成分分析（PCA）进行训练时，LDA对2D（86%）和3D（89%；P =.4）特征均取得了最高准确率。使用样条重采样训练的分类器的结果不如使用一维（1D）最近邻插值获得的结果准确（P<.05），而使用1D最近邻插值且未进行重采样训练的分类器的结果相似（P =.1）。与影像组学方法相比，对于2D和3D数据，经验较少的阅片者的主观视觉分析性能较低，经验丰富的阅片者的主观视觉分析性能较高。
结论
LGE的影像组学特征通过使用2D特征和RFE或3D特征和PCA能够高精度地区分MI和心肌炎。©RSNA，2019
Zotero 插件